© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27603
    Prev
    Next
    INDEX
    Explanations

    calls to action regarding enrollment and registration processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mour
    -0.07
    Forum
    -0.06
    ags
    -0.06
    kas
    -0.06
    undo
    -0.06
    èĩ
    -0.06
    anga
    -0.06
     Comfort
    -0.06
     Gig
    -0.06
     Ky
    -0.06
    POSITIVE LOGITS
    Äįin
    0.08
     physic
    0.07
     ÑĤÑı
    0.07
     ÐĹаг
    0.07
     competitiveness
    0.07
    ,application
    0.06
    ê¶ģ
    0.06
    -processing
    0.06
     mari
    0.06
    ÅŁam
    0.06
    Activations Density 0.016%

    No Known Activations